How to Generate CUDA Code for a Keras-TensorFlow Model - MATLAB
Current Time 0:00
Duration 0:00
Loaded: 0%
Stream Type LIVE
Remaining Time 0:00
 
1x
  • Chapters
  • descriptions off, selected
  • captions off, selected

      How to Generate CUDA Code for a Keras-TensorFlow Model

      This video walks step-by-step through the process of taking a deep network trained in Keras and Tensorflow and generating code to run directly on a GPU.

      You will learn how to use MATLAB® code generation tools in order to automatically generate C/C++ and CUDA code from your MATLAB program, so you can embed and run it in NVIDIA® GPUs or Intel® CPUs.

      Published: 18 Sep 2019

      Related Products

      Feedback

      Up Next:

      Virtual engineering technology has undergone rapid progress in recent years and has been widely accepted for commercial product development. Product design and manufacturing organizations are moving from the traditional multiple and serial test cycle

      Optimal Neural Network for Automotive Product Development

      Related Videos:

      In this webinar, you’ll see how MATLAB supports CUDA kernel development by providing a high level language and development environment for prototyping algorithms and incrementally developing and testing CUDA kernels.  Product demonstrations will high

      MATLAB for CUDA Programmers

      In this webinar we will demonstrate how to automatically generate C code from MATLAB functions. This capability is available for a subset of the MATLAB language called Embedded MATLAB

      Generate C Code from MATLAB Functions Using the Embedded...

      Use Embedded Coder to generate compiler directives for variant choices specified with Variant Source and Variant Sink blocks.

      Generate Code from Variant Sink and Source Blocks

      In part 9 of this webinar series, we discuss requirements-based testing of the cross-compiled executable object code.

      Model-Based Design for DO-178C Software Development with...

      View more related videos